© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 4772
    Prev
    Next
    INDEX
    Explanations

    treatment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     колл
    -0.07
    -order
    -0.07
    ôle
    -0.07
    医学院
    -0.07
     gathered
    -0.06
    -Mail
    -0.06
    tl
    -0.06
     barric
    -0.06
    	TArray
    -0.06
    ETY
    -0.06
    POSITIVE LOGITS
    .removeClass
    0.07
     bedrooms
    0.07
     größ
    0.07
     primo
    0.07
    ᵐ
    0.06
     letras
    0.06
    Except
    0.06
    Definition
    0.06
     Jess
    0.06
    Regex
    0.06
    Activations Density 0.045%

    No Known Activations